© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19330
    Prev
    Next
    INDEX
    Explanations

    phrases related to future actions or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    105
    +0.11
    0.5%
    144
    +0.10
    0.4%
    173
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.11
    0.02
    144
    +0.10
    0.01
    105
    +0.09
    0.01
    Negative Logits
     Sins
    -0.66
    ribe
    -0.64
    pel
    -0.63
    ipel
    -0.62
    senal
    -0.62
    rongh
    -0.57
    oat
    -0.57
    ories
    -0.56
     diam
    -0.56
    İĭ
    -0.56
    POSITIVE LOGITS
    aneously
    0.99
     thereafter
    0.95
     afterwards
    0.81
    ened
    0.80
     realised
    0.74
    eners
    0.73
     afterward
    0.71
     overdue
    0.70
    idious
    0.69
     forgotten
    0.69
    Activations Density 0.009%

    No Known Activations